Re:A polynomial autoencoder beats PCA on transformer embeddings
by pleshkov on Friday May 08, 2026 @11:33AM
(#48064610)
Fair point — lam is technically a hyperparameter. In practice I used lam=1e-3 (the default in the code) across all four models without tuning, and the gap to PCA is robust enough that small variations don't change the conclusion. So more accurately: "one hyperparameter with a benign default" rather than "no hyperparameters" — you're right I overstated.
[ Parent
| on HN ]
There are no comments on this comment yet.